Deep Learning and Computer Vision system for real-time autonomous retail stores using only RGB cameras.
Invited talk by Dr. Jun-Cheng Chen at Academia Sinica
Invited talk by Prof. Yen-Yu Lin at NYCU
\[**Thesis**\] My Ph.D. Dissertation at Georgia Tech.
Two methods (TS-LSTM and Temporal-Inception) to exploit spatiotemporal dynamics for activity recognition.
Cross-domain action recognition with new datasets and novel video-based DA approaches.
\[**ICCV 2019 (Oral)**\] Cross-domain action recognition with new datasets and novel attention-based DA approaches.
\[**SPIC 2019**\] Simple but effective CNN- and RNN-based approaches to exploit temporal dynamics for videos.
\[**CVPR 2014**\] Multi-modal adaptation with multiple kernel learning for action recognition.